Trending Research
Continuous Thought Machines
SakanaAI/continuous-thought-machines
•
•
The CTM has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique weight parameters to process a history of incoming signals; and (2) neural synchronization employed as a latent representation.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work.
OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
We hope OpenThinkIMG can serve as a foundational framework for advancing dynamic, tool-augmented visual reasoning, helping the community develop AI agents that can genuinely "think with images".
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
1zhou-Wang/MemVR
•
•
Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i. e., the generated content that is nonsensical or unfaithful to input sources.
Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs
Based on this notation and its transformations, we propose four optimization techniques that improve timing, area, and power consumption.
WorldPM: Scaling Human Preference Modeling
Motivated by scaling laws in language modeling that demonstrate how test loss scales as a power law with model and dataset sizes, we find that similar laws exist in preference modeling.
Hyperspectral Image Land Cover Captioning Dataset for Vision Language Models
We introduce HyperCap, the first large-scale hyperspectral captioning dataset designed to enhance model performance and effectiveness in remote sensing applications.
Dynamic Early Exit in Reasoning Models
iie-ycx/deer
•
•
Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks.
SkyReels-V2: Infinite-length Film Generative Model
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions.
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
However, such methods optimize only the final performance under a large and fixed token budget, which hinders efficiency in both training and deployment.
